Interpreting Machine Learning Predictions of Pb2+ Adsorption onto Biochars Produced by a Fluidized Bed System

IF 9.7 1区 环境科学与生态学 Q1 ENGINEERING, ENVIRONMENTAL
Suya Shi, Yaji Huang, Han Shen, Tengfei Zheng, Xinye Wang, Mengzhu Yu, Lingqin Liu
{"title":"Interpreting Machine Learning Predictions of Pb2+ Adsorption onto Biochars Produced by a Fluidized Bed System","authors":"Suya Shi, Yaji Huang, Han Shen, Tengfei Zheng, Xinye Wang, Mengzhu Yu, Lingqin Liu","doi":"10.1016/j.jclepro.2024.144551","DOIUrl":null,"url":null,"abstract":"Employing machine learning to predict the Pb<sup>2+</sup> adsorption capacity of biochars is an innovative pursuit in hazardous materials. This study compared artificial neural network (ANN), support vector regression (SVR) and random forest (RF) for Pb<sup>2+</sup> adsorption capacity by biochar from a fluidized bed system. Besides developing correlations for comparison, the RF model (R<sup>2</sup> = 0.984, RMSE=0.054) outperformed both ANN (R<sup>2</sup> = 0.908, RMSE=0.316) and SVR (R<sup>2</sup> =0.667) in predicting higher adsorption capacity. Based on the superior performance, the Shapley Additive Explanations (SHAP) were employed on RF. SHAP global explanations indicated that adsorption conditions contributed 69.03% and biochar characteristics contributed 30.21%to adsorption capacity, highlighting Dosage (D) and Carbon (C) as the crucial factors. Regarding biochar characteristics, element compositions contributed 76.59%. The single samples demonstrated that the final predictions align with the experimental results. The synergistic effect of dependence plot explains the Pb<sup>2+</sup> adsorption under varying parameter conditions, such as D&lt;1g/L, C&lt;45%, Pb<sub>in</sub>&gt;100mg/L, H&lt;2.5, t&gt;12h, T&gt;25°C, pH&gt;9, H/C&gt;0.4, the SHAP value is positive, contributing to an increase in adsorption capacity. Furthermore, a graphical user interface (GUI) leveraging SHAP model parameters predicts adsorbent performance, providing novel insights into optimizing biochars production. The obtained findings narrow the search for optimal biochars adsorbents and might guide laboratory experiments and engineering application of Pb<sup>2+</sup> removal using biochars.","PeriodicalId":349,"journal":{"name":"Journal of Cleaner Production","volume":"53 1","pages":""},"PeriodicalIF":9.7000,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Cleaner Production","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.1016/j.jclepro.2024.144551","RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ENVIRONMENTAL","Score":null,"Total":0}
引用次数: 0

Abstract

Employing machine learning to predict the Pb2+ adsorption capacity of biochars is an innovative pursuit in hazardous materials. This study compared artificial neural network (ANN), support vector regression (SVR) and random forest (RF) for Pb2+ adsorption capacity by biochar from a fluidized bed system. Besides developing correlations for comparison, the RF model (R2 = 0.984, RMSE=0.054) outperformed both ANN (R2 = 0.908, RMSE=0.316) and SVR (R2 =0.667) in predicting higher adsorption capacity. Based on the superior performance, the Shapley Additive Explanations (SHAP) were employed on RF. SHAP global explanations indicated that adsorption conditions contributed 69.03% and biochar characteristics contributed 30.21%to adsorption capacity, highlighting Dosage (D) and Carbon (C) as the crucial factors. Regarding biochar characteristics, element compositions contributed 76.59%. The single samples demonstrated that the final predictions align with the experimental results. The synergistic effect of dependence plot explains the Pb2+ adsorption under varying parameter conditions, such as D<1g/L, C<45%, Pbin>100mg/L, H<2.5, t>12h, T>25°C, pH>9, H/C>0.4, the SHAP value is positive, contributing to an increase in adsorption capacity. Furthermore, a graphical user interface (GUI) leveraging SHAP model parameters predicts adsorbent performance, providing novel insights into optimizing biochars production. The obtained findings narrow the search for optimal biochars adsorbents and might guide laboratory experiments and engineering application of Pb2+ removal using biochars.
流化床系统对生物炭吸附Pb2+的机器学习预测
利用机器学习来预测生物炭对Pb2+的吸附能力是危险材料领域的一项创新追求。本研究比较了人工神经网络(ANN)、支持向量回归(SVR)和随机森林(RF)对流化床生物炭吸附Pb2+能力的影响。除了建立相关性进行比较外,RF模型(R2 = 0.984, RMSE=0.054)在预测更高吸附容量方面优于ANN模型(R2 = 0.908, RMSE=0.316)和SVR模型(R2 =0.667)。基于其优越的性能,我们将Shapley加性解释(SHAP)应用于射频分析。SHAP全局解释表明,吸附条件对吸附量的贡献为69.03%,生物炭特性对吸附量的贡献为30.21%,其中剂量(D)和碳(C)是影响吸附量的关键因素。元素组成对生物炭特性的贡献率为76.59%。单个样本表明,最终预测与实验结果一致。依赖性图的协同效应解释了不同参数条件下,如D<;1g/L, C<45%, Pbin>100mg/L, H<2.5, t>12h, t> 25°C, pH>9, H/C>0.4,对Pb2+的吸附,SHAP值为正,有助于吸附容量的增加。此外,图形用户界面(GUI)利用SHAP模型参数预测吸附剂性能,为优化生物炭生产提供了新的见解。所得结果缩小了寻找最佳生物炭吸附剂的范围,并可能指导生物炭去除Pb2+的实验室实验和工程应用。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Journal of Cleaner Production
Journal of Cleaner Production 环境科学-工程:环境
CiteScore
20.40
自引率
9.00%
发文量
4720
审稿时长
111 days
期刊介绍: The Journal of Cleaner Production is an international, transdisciplinary journal that addresses and discusses theoretical and practical Cleaner Production, Environmental, and Sustainability issues. It aims to help societies become more sustainable by focusing on the concept of 'Cleaner Production', which aims at preventing waste production and increasing efficiencies in energy, water, resources, and human capital use. The journal serves as a platform for corporations, governments, education institutions, regions, and societies to engage in discussions and research related to Cleaner Production, environmental, and sustainability practices.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信